activity
20162026
most citedThe Dynamic of Consensus in Deep Networks and the Identification of Noisy Labels

2 citations · 7 across the 13 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2023

Semi-Supervised Learning in the Few-Shot Zero-Shot Scenario

Noam Fluss, Guy Hacohen, Daphna Weinshall

Semi-Supervised Learning (SSL) is a framework that utilizes both labeled and unlabeled data to enhance model performance. Conventional SSL methods operate under the assumption that…

cs.CV20201 cited

Boosting the Performance of Semi-Supervised Learning with Unsupervised Clustering

Boaz Lerner, Guy Shiran, Daphna Weinshall

Recently, Semi-Supervised Learning (SSL) has shown much promise in leveraging unlabeled data while being provided with very few labels. In this paper, we show that ignoring the lab…

cs.CV2020

Multiclass non-Adversarial Image Synthesis, with Application to Classification from Very Small Sample

Itamar Winter, Daphna Weinshall

The generation of synthetic images is currently being dominated by Generative Adversarial Networks (GANs). Despite their outstanding success in generating realistic looking images,…

cs.CV2019

Multi-Modal Deep Clustering: Unsupervised Partitioning of Images

Guy Shiran, Daphna Weinshall

The clustering of unlabeled raw images is a daunting task, which has recently been approached with some success by deep learning methods. Here we propose an unsupervised clustering…

cs.CV20191 cited

Blurred Images Lead to Bad Local Minima

Gal Katzhendler, Daphna Weinshall

Blurred Images Lead to Bad Local Minima

cs.CV2016

Novelty Detection in MultiClass Scenarios with Incomplete Set of Class Labels

Nomi Vinokurov, Daphna Weinshall

We address the problem of novelty detection in multiclass scenarios where some class labels are missing from the training set. Our method is based on the initial assignment of conf…